Integrating multi-omics and machine learning survival frameworks to build a prognostic model based on immune function and cell death patterns in a lung adenocarcinoma cohort

Aug 5, 2026

Upload by Aria

Programmed cell death (PCD) and immune-related genes are critical in lung adenocarcinoma (LUAD) progression, yet the prognostic value of their interaction remains unclear. This original research integrates cell-death genes, immune genes, methylation, and somatic mutation data with 10 clustering algorithms and machine-learning survival frameworks to derive LUAD molecular subtypes and build an immune-associated programmed cell death model (PIGRS). PIGRS identifies 15 high-impact genes with strong prognostic performance, and in vitro evidence supports PSME3 as a novel factor potentially linked to PI3K/AKT/Bcl-2 signaling.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Introduction

Background: PCD and immune genes in LUAD

Methods

Molecular typing using multi-omics and clustering

Machine-learning survival framework and PIGRS construction

In vitro validation focused on PSME3

Results

TCGA-LUAD subtypes and prognosis differences

PIGRS gene set and prognostic performance

Discussion

Molecular subtypes, clinical significance, and PSME3 pathway hypothesis

TYPE Original Research PUBLISHED 13 September 2024 DOI 10.3389/fimmu.2024.1460547 OPEN ACCESS EDITED BY Inimary Toby-Ogundeji, University of Dallas, United States REVIEWED BY Yang Cheng, Air Force Medical University, China João Pessoa, University of Aveiro, Portugal *CORRESPONDENCE Xiaojing Wang [wangxiaojing8888@163.com](wangxiaojing8888@163.com)[ ](wangxiaojing8888@163.com)Chaoqun Lian [lianchaoqun@bbmc.edu.cn](lianchaoqun@bbmc.edu.cn) †These authors have contributed equally to this work RECEIVED 06 July 2024 ACCEPTED 23 August 2024 PUBLISHED 13 September 2024 CITATION Xie Y, Chen H, Tian M, Wang Z, Wang L, Zhang J, Wang X and Lian C (2024) Integrating multi-omics and machine learning survival frameworks to build a prognostic model based on immune function and cell death patterns in a lung adenocarcinoma cohort. Front. Immunol. 15:1460547 . doi: 10.3389/fimmu.2024.1460547 COPYRIGHT © 2024 Xie, Chen, Tian, Wang, Wang, Zhang, Wang and Lian. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Integrating multi-omics and machine learning survival frameworks to build a prognostic model based on immune function and cell death patterns in a lung adenocarcinoma cohort Yiluo Xie 1,2†, Huili Chen 3†, Mei Tian 1, Ziqang Wang 3, Luyao Wang 4, Jing Zhang 4, Xiaojing Wang 1* and Chaoqun Lian 3* 1Anhui Province Key Laboratory of Clinical and Preclinical Research in Respiratory Disease, MolecularDiagnosis Center, Joint Research Center for Regional Diseases of Institute of Health and Medicine (IHM), First Afﬁliated Hospital of Bengbu Medical University, Bengbu, China, 2 Department of Clinical Medicine, Bengbu Medical University, Bengbu, China, 3 Research Center of Clinical Laboratory Science, Bengbu Medical University, Bengbu, China, 4 Department of Genetics, School of Life Sciences, Bengbu Medical University, Bengbu, China Introduction: The programmed cell death (PCD) plays a key role in the development and progression of lung adenocarcinoma. In addition, immunerelated genes also play a crucial role in cancer progression and patient prognosis. However, further studies are needed to investigate the prognostic signiﬁcance of the interaction between immune-related genes and cell death in LUAD. Methods: In this study, 10 clustering algorithms were applied to perform molecular typing based on cell death-related genes, immune-related genes, methylation data and somatic mutation data. And a powerful computational framework was used to investigate the relationship between immune genes and cell death patterns in LUAD patients. A total of 10 commonly used machine learning algorithms were collected and subsequently combined into 101 unique combinations, and we constructed an immune-associated programmed cell death model (PIGRS) using the machine learning model that exhibited the best performance. Finally, based on a series of in vitro experiments used to explore the role of PSME3 in LUAD. Results: We used 10 clustering algorithms and multi-omics data to categorize TCGA-LUAD patients into three subtypes. patients with the CS3 subtype had the best prognosis, whereas patients with the CS1 and CS2 subtypes had a poorer prognosis. PIGRS, a combination of 15 high-impact genes, showed strong prognostic performance for LUAD patients. PIGRS has a very strong prognostic efﬁcacy compared to our collection. In conclusion, we found that PSME3 has been little studied in lung adenocarcinoma and may be a novel prognostic factor in lung adenocarcinoma. Frontiers in Immunology 01 [frontiersin.org](frontiersin.org) Disc

FAQs

What is the study focused on in LUAD prognosis?

The study investigates how immune-related genes interact with programmed cell death patterns to improve prognostic modeling in lung adenocarcinoma cohorts.

How were LUAD subtypes and the PIGRS model constructed?

Ten clustering algorithms were applied using cell death–related genes, immune-related genes, methylation, and somatic mutation data, followed by combining machine-learning survival algorithms to build the immune-associated programmed cell death model (PIGRS).

What do the results indicate about PIGRS and PSME3?

PIGRS, built from 15 high-impact genes, shows strong prognostic performance across LUAD patients, and PSME3 is highlighted as a potential novel prognostic factor supported by experimental findings.

Aug 5, 2026

Upload by Aria